01
Why naive RAG fails for coding agents—and what Satori does instead
Why fixed text chunks are weak evidence for code changes, and how Satori combines symbol-aware chunking, hybrid retrieval, freshness checks, and exact bounded reads.
Writing tag
Writing tagged "Systems"
3 notes from the writing archive.
02
When index cleanup lies, agents make unsafe decisions
A practical note on debugging Satori's clear/reindex path by treating remote vector state as an explicit lifecycle contract.
03
Why MCP CLIs fail when stdout is treated like logs
Notes on turning Satori's shell CLI into a disciplined MCP wrapper with stdout safety, dynamic bootstrap, and deterministic exit behavior.
/ Topics